debug-gha-analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to use gh CLI commands (e.g., "gh run view", "gh run list", "gh pr list", git diff) to fetch GitHub run logs, job details, commits and PRs from public GitHub repositories—untrusted, user-generated content the agent is expected to read and that can materially influence debugging decisions.